Skip to main content

A unified approach to explain the output of any machine learning model.

Project description

SHAP (SHapley Additive exPlanations) is a unified approach to explain the output of any machine learning model. SHAP connects game theory with local explanations, uniting several previous methods and representing the only possible consistent and locally accurate additive feature attribution method based on expectations.

Project details


Release history Release notifications | RSS feed

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

shap-0.36.0.tar.gz (319.8 kB view details)

Uploaded Source

Built Distributions

shap-0.36.0-cp38-cp38-win_amd64.whl (370.2 kB view details)

Uploaded CPython 3.8Windows x86-64

shap-0.36.0-cp37-cp37m-win_amd64.whl (369.9 kB view details)

Uploaded CPython 3.7mWindows x86-64

shap-0.36.0-cp36-cp36m-win_amd64.whl (369.9 kB view details)

Uploaded CPython 3.6mWindows x86-64

File details

Details for the file shap-0.36.0.tar.gz.

File metadata

  • Download URL: shap-0.36.0.tar.gz
  • Upload date:
  • Size: 319.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/3.2.0 pkginfo/1.5.0.1 requests/2.24.0 setuptools/49.6.0 requests-toolbelt/0.9.1 tqdm/4.48.2 CPython/3.6.7

File hashes

Hashes for shap-0.36.0.tar.gz
Algorithm Hash digest
SHA256 30d5f5860e7d7787eeed09592e2b3bbd68816b0d3589f2eda6adc7663448217f
MD5 f7570857f89daf6a6277c0fb54053edb
BLAKE2b-256 d21737ee6c79cafbd9bb7423b54e55ea90beec66aa7638664d607bcc28de0bae

See more details on using hashes here.

File details

Details for the file shap-0.36.0-cp38-cp38-win_amd64.whl.

File metadata

  • Download URL: shap-0.36.0-cp38-cp38-win_amd64.whl
  • Upload date:
  • Size: 370.2 kB
  • Tags: CPython 3.8, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.8

File hashes

Hashes for shap-0.36.0-cp38-cp38-win_amd64.whl
Algorithm Hash digest
SHA256 b17d1ad56a20f83854217f3b799637220981d2798269e82860cc01afddddef7b
MD5 ba300d1dac9a83ac1f01d8ba498d5c07
BLAKE2b-256 578cbf13595a7c48ae999fa85e60570726373e678ffe2b6dd2ab32d6e3535d1a

See more details on using hashes here.

File details

Details for the file shap-0.36.0-cp37-cp37m-win_amd64.whl.

File metadata

  • Download URL: shap-0.36.0-cp37-cp37m-win_amd64.whl
  • Upload date:
  • Size: 369.9 kB
  • Tags: CPython 3.7m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.7

File hashes

Hashes for shap-0.36.0-cp37-cp37m-win_amd64.whl
Algorithm Hash digest
SHA256 15a90385ed1b230a62beac27ccb73a2e06aa52d4519b869ba178fd7f05634e12
MD5 7dfc78f16bdaa7a5cdc65a5ada692f96
BLAKE2b-256 5cca46c429a403487a8bab7db4c5a9b556a61cbc462e59654fd8301abc106b5b

See more details on using hashes here.

File details

Details for the file shap-0.36.0-cp36-cp36m-win_amd64.whl.

File metadata

  • Download URL: shap-0.36.0-cp36-cp36m-win_amd64.whl
  • Upload date:
  • Size: 369.9 kB
  • Tags: CPython 3.6m, Windows x86-64
  • Uploaded using Trusted Publishing? No
  • Uploaded via: Python-urllib/3.6

File hashes

Hashes for shap-0.36.0-cp36-cp36m-win_amd64.whl
Algorithm Hash digest
SHA256 d3d48f7a9507b3ea5e4c2831e9cacd3b620c390bafb51d01004abd3d5d8e571f
MD5 9e5de62da32c8e907f3bcc18adb75811
BLAKE2b-256 a9b28cae3ee73a6f6fcfaaa792dbd3f6ca8d9725429c5bc4cd8e918f4b0f7ee9

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page